OpenSep: a generalizable open source pipeline for SOFA score calculation and Sepsis-3 classification. Issue 4 (21st December 2022)

• Record Type: Journal Article
• Authors: Hofford, Mackenzie R; Yu, Sean C; Johnson, Alistair E W; Lai, Albert M; Payne, Philip R O; Michelson, Andrew P
• Is Part Of: JAMIA open. Volume 5:Issue 4(2022)
• Publication Date: 2022-12-21
• Subjects: Sepsis -- Sepsis-3 -- SOFA -- MIMIC -- critical care -- phenotyping; Medical informatics -- Periodicals; 610.285
• DOI: 10.1093/jamiaopen/ooac105
• Languages: English
• ISSNs: 2574-2531

Abstract

Abstract: EHR-based sepsis research often uses heterogeneous definitions of sepsis leading to poor generalizability and difficulty in comparing studies to each other. We have developed OpenSep, an open-source pipeline for sepsis phenotyping according to the Sepsis-3 definition, as well as determination of time of sepsis onset and SOFA scores. The Minimal Sepsis Data Model was developed alongside the pipeline to enable the execution of the pipeline to diverse sources of electronic health record data. The pipeline's accuracy was validated by applying it to the MIMIC-IV version 1.0 data and comparing sepsis onset and SOFA scores to those produced by the pipeline developed by the curators of MIMIC. We demonstrated high reliability between both the sepsis onsets and SOFA scores, however the use of the Minimal Sepsis Data model developed for this work allows our pipeline to be applied to more broadly to data sources beyond MIMIC. Lay Summary: Despite significant interest in the prediction, identification, and prompt treatment of sepsis, the definition of sepsis varies greatly between different studies. Here we present an open source pipeline for determining the presence and time of onset of sepsis. We have designed this pipeline to require the minimal possible information to make this determination to avoid the need for excessive data manipulation. The proposed pipeline shows good alignment with preciously a previously published Sepsis pipeline that is much more difficult to apply to diverse datasets due to its complex data model. We hope that by making this work publically available we can reduce redundant effort and improve consistency of Sepsis definitions used in the literature.